by Samir Saci
Tags: Productivity, Pomodoro, Organization Context Hey! I’m Samir, a Supply Chain Engineer and Data Scientist from Paris, founder of LogiGreen Consulting 🌱 A significant improvement in my productivity came from following the Pomodoro Technique. What is the Pomodoro Technique? The Pomodoro Technique is a time management method that breaks your workday into 25-minute focus intervals followed by short breaks. After 4 cycles, you take a longer break to recharge. It helps maintain concentration while preventing burnout. I’ve used this technique with web apps to receive break/work notifications. But I always wished I had a way to track my sessions for self-assessment. > Let’s use n8n to boost our productivity and log our deep work sessions automatically! 📬 For business inquiries, you can add me on Here Who Is This Template For? I built this workflow for creators, freelancers, students, and professionals who love the Pomodoro technique but want more than just timers — they want data. This template helps you: Track every deep work session automatically Store logs in Google Sheets for later analysis Stay in control via Telegram commands There is no need to pay for premium apps. It’s all free and powered by n8n. How Does It Work? This Telegram bot tracks your Pomodoro sessions and sends you alerts during the process. Here’s what happens: A user sends /start to the bot. It launches a 25-minute deep work timer. After 25 minutes, the bot sends a break reminder. After four cycles, a long break is triggered and the session is logged. The session is automatically recorded to Google Sheets with (Date & Time, User ID, Pomodoro count, Session ID, Duration of focus and breaks) What Gets Tracked? | Field | Description | |-------------------|--------------------------------------| | Date & Time | When the session was logged | | User ID | Your Telegram ID | | Block Type | Deep Work or Short Break | Pomodoro Count | Number of cycles completed | | Working Session ID | Unique ID for each session | | Focus Duration | Length of each deep work session | | Break Duration | Short or long break info | You can use this workflow as a base to bring additional features like: Connecting with tasks from Google Task Send automated productivity reports to monitor your activity Link a Pomodoro with a task using Google Calendar What Do I Need to Start? This workflow is beginner-friendly — no coding required. Google Drive API* and *Google Sheet API** credentials A Google Sheet set up to log sessions (with the columns of the table above) API Credentials: Google Sheets API (OAuth2) Telegram Bot Token Telegram app to chat with the bot > The template is plug-and-play. Just follow the sticky notes in the n8n editor to configure it. Next Steps Follow the sticky notes in the n8n workflow editor to: Set your credentials Connect your Google Sheet Initialize the static data Launch your first /start command on Telegram 🎥 Watch My Tutorial 🚀 Curious how n8n can supercharge productivity and learning skills?? 📬 Let’s connect on LinkedIn This workflow has been created with N8N 1.82.1 Submitted: March 24th, 2025
by tbphp
Overview This n8n template monitors specified GitHub repositories. When a new release is published, it automatically fetches the information, uses AI (Google Gemini by default) to summarize and translate it into Chinese, and sends a formatted notification to a designated Slack channel. Core Features: Automated Monitoring**: Checks for updates on a predefined schedule. Intelligent Processing**: Uses AI to extract key information and translate. Error Handling**: Sends an error notification if fetching RSS for a single repository fails, without affecting others. Duplicate Prevention**: Remembers the last processed release ID using Redis to ensure only new content is pushed. Prerequisites Slack**: Configure your Slack app credentials in n8n. Redis**: Have an available Redis service and configure its credentials in n8n. AI Provider (Gemini)**: Configure credentials for Google Gemini (or your chosen AI model) in n8n. Configuration Instructions After importing the template, you need to modify the following key nodes: Cron Trigger: Adjust the Rule setting to change the update check frequency (default is 0 */10 9-23 * * *, checking every 10 minutes between 9 AM and 11 PM daily). GitHub Config (Repository List - Code Node): Edit the JavaScript array within this node's code area. Modify or add the repositories you want to follow. Each repository object needs a name (custom display name) and github (format: owner/repo). Example: { "name": "n8n", // Custom display name "github": "n8n-io/n8n" // GitHub path }, { "name": "LobeChat", "github": "lobehub/lobe-chat" } // ... add more repositories Redis and Redis2 (Redis Connection): Select your configured Redis credentials in both nodes. Gemini (AI Model): Select your configured Google Gemini credentials. (Optional) Replace with a different supported AI model node and select its credentials. Information Extractor (AI Processing & Translation): Main Configuration: Review the System Prompt. By default, it asks the AI to extract information and translate it into Chinese. Modify this prompt if you need a different language or summary style. Send Message and Send Error (Slack Notifications): Select your configured Slack credentials in both Slack nodes. Set the target Channel ID for notifications. Workflow Overview Start: Cron Trigger initiates the workflow on schedule. Load Config: GitHub Config provides the list of repositories to monitor. Loop: The Loop node iterates through each repository. Fetch & Check: The RSS node attempts to fetch the repository's releases feed. If No Error checks for success: Failure: Send Error posts an error to Slack, skips this repository. Success: Continues. Check for New Release: The Redis node retrieves the last recorded Release ID for this repository. The If New node compares the latest Release ID with the recorded ID: Different IDs (New Release): Proceeds to processing. Same ID (Already Processed): Skips this repository. Process & Notify (Only for New Releases): Information Extractor (with Gemini) extracts, summarizes, and translates the content. The Code node formats the information into Slack Block Kit. Send Message sends the formatted message to Slack. The Redis2 node stores the current Release ID in Redis. End: The workflow finishes after processing all repositories. Conclusion Once configured, this template automates GitHub release monitoring, uses AI to distill key information, and delivers it efficiently to your Slack workspace.
by Airtop
About The ICP Company Scoring Automation Sorting through lists of potential leads manually to determine who's truly worth your sales team's time isn't just tedious, it's incredibly inefficient. Without proper qualification, your team might spend hours pursuing prospects who aren't the right fit for your product, while ideal customers slip through the cracks. How to Automate Identifying Your Ideal Customers With this automation, you'll learn how to automatically score and prioritize leads using data extracted directly from LinkedIn profiles via Airtop's integration with n8n. By the end, you'll have a fully automated workflow that analyzes prospects and calculates an Ideal Customer Profile (ICP) score, helping your sales team focus on high-potential opportunities. What You'll Need A free Airtop API key A copy of this Google Sheets Understanding the Process This automation transforms how you qualify and prioritize leads by extracting real-time, accurate information directly from LinkedIn profiles. Unlike static databases that quickly become outdated, this workflow taps into the most current professional information available. The workflow in this template: Uses Airtop to extract comprehensive LinkedIn profile data Analyzes the data to calculate an ICP score based on AI interest, technical depth, and seniority Updates your Google Sheet with the enriched data and the ICP Company score Company ICP Scoring Workflow Our company-focused workflow analyzes company LinkedIn profiles with a comprehensive set of criteria: Company Identity Extraction Company Scale Assessment Business Classification Technical Sophistication Assessment Investment Profile To then calculate the ICP Scoring, it will focus on: AI Implementation Level: Low-5 pts, Medium-10 pts, High-25 pts Technical Sophistication: Basic-5 pts, Intermediate-15 pts, Advanced-25 pts, Expert-35 pts Employee Count: 0-9 employees-5 pts, 10-150 employees-25 pts, 150+ employees-30 pts Automation Agency Status: True-20 pts, False-0 pts Geography: US/Europe Based-10 pts, Other-0 pts Setting Up Your Automation We've created ready-to-use templates for both person and company ICP scoring. Here's how to get started: Configure your connections Connect your Google Sheets account Add your Airtop API key (obtain from the Airtop dashboard) Set up your Google Sheet Ensure your Google Sheet has the necessary columns for input data and result fields Ensure that columns Linkedin_URL_Company and ICP_Score_Company exist at least Configure the Airtop module Set up the Airtop module to use the appropriate LinkedIn extraction prompt Use our provided prompt that extracts company profile data Customization Options While our templates work out of the box, you might want to customize them for your specific needs: Modify the ICP scoring criteria: Adjust the point values or add additional criteria specific to your business Add notification triggers: Set up Slack or email notifications for high-value leads that exceed a certain ICP threshold Implement batch processing: Modify the workflow to process leads in batches to optimize performance Add conditional logic: Create different scoring models for different industries or product lines Integrate with your CRM: Integrate this automation with your preferred CRM to get the details added automatically for you Real-World Applications Here's how businesses are using this automation: AI Sales Platform: A B2B AI company could implement this workflow to process their trade show lead list of contacts. Within hours, they can identify the top 50 prospects based on ICP score. SaaS Analytics Tool: A SaaS company could implement LinkedIn enrichment to identify which companies fit best. The automation processes weekly leads and categorizes them into high, medium, and low priority tiers, allowing their sales team to focus on the most promising opportunities first. Best Practices To get the most out of this automation: Review and refine your ICP criteria quarterly: What constitutes an ideal customer may evolve as your product and market develop Create tiered follow-up processes: Develop different outreach strategies based on ICP score ranges Perform regular data validation: Periodically check the accuracy of the automated scoring against your actual sales results What's Next? Now that you've automated your ICP scoring with LinkedIn data, you might be interested in: Setting up automated outreach sequences based on ICP score thresholds Creating custom reporting dashboards to track conversion rates by ICP segment Expanding your scoring model to include additional data sources Implementing lead assignment automation based on ICP scores Happy automating!
by Airtop
About The ICP Person Scoring Automation Sorting through lists of potential leads manually to determine who's truly worth your sales team's time isn't just tedious, it's incredibly inefficient. Without proper qualification, your team might spend hours pursuing prospects who aren't the right fit for your product, while ideal customers slip through the cracks. How to Automate Identifying Your Ideal Customers With this automation, you'll learn how to automatically score and prioritize leads using data extracted directly from LinkedIn profiles via Airtop's built-in integration with n8n. By the end, you'll have a fully automated workflow that analyzes prospects and calculates an Ideal Customer Profile (ICP) score, helping your sales team focus on high-potential opportunities. What You'll Need A free Airtop API key A copy of this Google Sheets Understanding the Process This automation transforms how you qualify and prioritize leads by extracting real-time, accurate information directly from LinkedIn profiles. Unlike static databases that quickly become outdated, this workflow taps into the most current professional information available. The workflow in this template: Uses Airtop to extract comprehensive LinkedIn profile data Analyzes the data to calculate an ICP score based on AI interest, technical depth, and seniority Updates your Google Sheet with the enriched data and the ICP score Person ICP Scoring Workflow Our person-focused workflow evaluates individual LinkedIn profiles to determine how well they match your ideal customer profile by: Extracting data for each individual Analyzing their profile to determine seniority and technical depth The system then automatically calculates an ICP score based on the following criteria: AI Interest: beginner-5 pts, intermediate-10 pts, advanced-25 pts, expert-35 pts Technical Depth: basic-5 pts, intermediate-15 pts, advanced-25 pts, expert-35 pts Seniority Level: junior-5 pts, mid-level-15 pts, senior-25 pts, executive-30 pts Setting Up Your Automation Here's how to get started: Configure your connections Connect your Google Sheets account Add your Airtop API key (obtain from the Airtop dashboard) Set up your Google Sheet Ensure your Google Sheet has the necessary columns for input data and result fields Ensure that columns Linkedin_URL_Person and ICP_Score_Person exist at least Configure the Airtop module Set up the Airtop module to use the appropriate LinkedIn extraction prompt Use our provided prompt that extracts individual profile data Customization Options While our templates work out of the box, you might want to customize them for your specific needs: Modify the ICP scoring criteria: Adjust the point values or add additional criteria specific to your business Add notification triggers: Set up Slack or email notifications for high-value leads that exceed a certain ICP threshold Implement batch processing: Modify the workflow to process leads in batches to optimize performance Add conditional logic: Create different scoring models for different industries or product lines Integrate with your CRM: Integrate this automation with your preferred CRM to get the details added automatically for you Real-World Applications Here's how businesses are using this automation: AI Sales Platform: A B2B AI company could implement this workflow to process their trade show lead list of contacts. Within hours, they can identify the top 50 prospects based on ICP score. SaaS Analytics Tool: A SaaS company could implement LinkedIn enrichment to identify which companies fit best. The automation processes weekly leads and categorizes them into high, medium, and low priority tiers, allowing their sales team to focus on the most promising opportunities first. Best Practices To get the most out of this automation: Review and refine your ICP criteria quarterly: What constitutes an ideal customer may evolve as your product and market develop Create tiered follow-up processes: Develop different outreach strategies based on ICP score ranges Perform regular data validation: Periodically check the accuracy of the automated scoring against your actual sales results What's Next? Now that you've automated your ICP scoring with LinkedIn data, you might be interested in: Setting up automated outreach sequences based on ICP score thresholds Creating custom reporting dashboards to track conversion rates by ICP segment Expanding your scoring model to include additional data sources Implementing lead assignment automation based on ICP scores Happy automating!
by Jakkrapat Ampring
Main Use Case This workflow enables automated, AI-assisted replies to users messaging a LINE Official Account, while storing and referencing chat history from Google Sheets to maintain context. Ideal for businesses or support teams that want to provide smart, personalized customer interactions using AI with memory. How It Works (Step-by-Step) Connect to LINE Official Account's API A Webhook listens for incoming messages from users on LINE. When a message is received, it triggers the workflow. Prepare the Data An Edit Fields module structures incoming data (e.g. extracts user ID, message content). This ensures data is clean and usable downstream. Retrieve Chat History The user’s previous conversations are fetched from a Google Sheet. This ensures the AI has memory and can continue conversations contextually. Prepare Prompt The retrieved chat history is combined with the new message to form a complete prompt for the AI. Example format: “User previously said X. Now they said Y. How should we respond?” AI Agent: Google Gemini The formatted prompt is passed to an AI Agent (Google Gemini Chat Model). The AI generates a response based on the message + history. Tools used: Chat ModeMemory, ToolOutputParser for accurate replies. Split & Clean History The conversation history is split into smaller chunks for cleaning and storage. This ensures the Google Sheet remains readable and manageable over time. Save Chat History The cleaned new message and AI reply are saved to Google Sheets. This updates the chat history for future context. Send Reply to LINE The AI-generated reply is sent back to the user via a POST HTTP Request to the LINE Messaging API. How to Set Up Prerequisites: LINE Official Account Google Sheet to store chat history Google Gemini API or AI agent with context memory Automation platform (e.g., n8n, as this seems visually similar) Step-by-Step: Create a Webhook on LINE: Set the webhook URL to your automation service. Enable webhook events. Design Your Google Sheet: Create a sheet with columns: User ID, Timestamp, Message, AI Reply. Set Up Modules in Automation Platform: Webhook: receives user messages. Edit Fields: extract user ID and message. Google Sheets Read: fetch message history. Prompt Composer: format prompt using past history + new message. AI Agent: connect to Google Gemini for smart replies. Split & Clean: clean and chunk history if needed. Google Sheets Write: save the updated conversation. HTTP Request: send reply to LINE via Messaging API. Test Your Workflow: Send a message from LINE. Watch the full loop: receive → process → AI → store → reply. Deploy & Monitor: Ensure error handling is in place (e.g., for blank messages or failed API calls). Regularly check your Google Sheets for storage limits. (If limits reached, you can increase the history row.) 📦 Benefits Maintains context in conversations Personalized, AI-driven responses Easy history tracking via Google Sheets Fully automated and scalable
by PiAPI
What does the workflow do? This workflow is designed to generate high-quality short videos, primarily uses GPT-4o-mini (unofficial), Midjourney (unofficial) and Kling (unofficial) APIs from PiAPI and Creatomate API mainly for content creator, social media bloggers and short-form video creators. Through this short video workflow, users can quickly validate their creative ideas and focus more on enhancing the quality of their video concepts. Who is the workflow for? Social Media Influencers: produce content videos based on inspiration efficiently. Vloggers: generate vlogs based on inspiration. Educational Creators: explain specific topics via animated short videos or demonstrate a specific imagined scenario to students for enhanced educational impact. Advertising Agencies: generate short videos based on specific products. AI Tool Developers: automatically generate product demo videos. Step-by-step Instructions Fill in X-API-key of PiAPI account in Basic Params node. Fill in the scenario of the image and video prompt. Set a video template on Creatomate and make an API call in the final node with core and processing modules provided in Creatomate. Before full video generation, you can first use basic assets in Creatomate for a prototype demo, then integrate with n8n after verifying the expected results. Fill in your Creatomate account settings following the image guildline. Click Test Workflow and wait for a generation (within 10~20min). In this workflow, we've established a basic structure for image-to-video generation with subtitle integration. You can further enhance it by adding music nodes using either PiAPI's audio models or your preferred music solution. All video elements will ultimately be composited through Creatomate. For best practice, please refer to PiAPI's official API documentation or Creatomate's API documentation to comprehend more use cases. Use Case Params Settings style: a children’s book cover, ages 6-10. --s 500 --sref 4028286908 --niji 6 character: A gentle girl and a fluffy rabbit explore a sunlit forest together, playing by a sparkling stream situational_keywords: Butterflies flutter around them as golden sunlight filters through green leaves. Warm and peaceful atmosphere Output Video
by Preston Zeller
How It Works This workflow automates the entire property lead generation process in a few simple steps: Property Search: Connects to BatchData's Property Search API with customizable parameters (location, property type, value range, equity percentage, etc.) Lead Filtering & Scoring: Processes results to identify the most promising leads based on criteria like absentee ownership, years owned, equity percentage, and tax status. Each property receives a lead score to prioritize follow-up. Skip Tracing: Automatically retrieves owner contact information (phone, email, mailing address) for each qualified property. Data Formatting: Structures all property and owner data into a clean, organized format ready for your systems. Multi-Channel Output: Generates an Excel spreadsheet with all lead details Pushes leads directly to your CRM (configurable for HubSpot, Salesforce, etc.) Sends a summary email with the spreadsheet attached The workflow can run on a daily schedule or be triggered manually as needed. All parameters are easily configurable through dedicated nodes, requiring no coding knowledge. Who's It For This workflow is perfect for: Real Estate Investors looking to find off-market properties with motivated sellers Real Estate Agents who want to generate listing leads from distressed or high-equity properties Investment Companies that need regular lead flow for acquisitions Real Estate Marketers who run targeted campaigns to property owners Wholesalers seeking to build a pipeline of potential deals Property Service Providers (roof repair, renovation contractors, etc.) who target specific property types Anyone who needs reliable, consistent lead generation for real estate without the manual work of searching, filtering, and organizing property data will benefit from this automation. About BatchData BatchData is a comprehensive property data provider that offers access to nationwide property information, owner details, and skip tracing services. Key features include: Extensive Database: Covers 150+ million properties across all 50 states Rich Property Data: Includes ownership information, tax records, sales history, valuation estimates, equity positions, and more Skip Tracing Services: Provides owner contact information including phone numbers, email addresses, and mailing addresses Distressed Property Indicators: Flags for pre-foreclosure, tax delinquency, vacancy, and other motivation factors RESTful API: Professional API for programmatic access to all property data services Regular Updates: Continuously refreshed data for accurate information BatchData's services are designed for real estate professionals who need reliable property and owner information to power their marketing and acquisition strategies. Their API-first approach makes it ideal for workflow automation tools like N8N.
by David Roberts
The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.
by Dataki
This workflow allows you to easily evaluate and compare the outputs of two language models (LLMs) before choosing one for production. In the chat interface, both model outputs are shown side by side. Their responses are also logged into a Google Sheet, where they can be evaluated manually or automatically using a more advanced model. Use Case You're developing an AI agent, and since LLMs are non-deterministic, you want to determine which one performs best for your specific use case. This template is designed to help you compare them effectively. How It Works The user sends a message to the chat interface. The input is duplicated and sent to two different LLMs. Each model processes the same prompt independently, using its own memory context. Their answers, along with the user input and previous context, are logged to Google Sheets. You can review, compare, and evaluate the model outputs manually (or automate it later). In the chat, both responses are also shown one after the other for direct comparison. How To Use It Copy this Google Sheets template (File > Make a Copy). Set up your System Prompt and Tools in the AI Agent node to suit your use case. Start chatting! Each message will trigger both models and log their responses to the spreadsheet. Note: This version is set up for two models. If you want to compare more, you’ll need to extend the workflow logic and update the sheet. About Models You can use OpenRouter or Vertex AI to test models across providers. If you're using a node for a specific provider, like OpenAI, you can compare different models from that provider (e.g., gpt-4.1 vs gpt-4.1-mini). Evaluation in Google Sheets This is ideal for teams, allowing non-technical stakeholders (not just data scientists) to evaluate responses based on real-world needs. Advanced users can automate this evaluation using a more capable model (like o3 from OpenAI), but note that this will increase token usage and cost. Token Considerations Since each input is processed by two different models, the workflow will consume more tokens overall. Keep an eye on usage, especially if working with longer prompts or running multiple evaluations, as this can impact cost.
by Alfonso Corretti
Gmail to Vector Embeddings with PGVector and Ollama Who is this for? Everyone! Did you dream of asking an AI "what hotel did I stay in for holidays last summer?" or "what were my marks last semester like?". Dream no more, as vector similarity searches and this workflow are the foundations to make it possible (as long as the information appears in your e-mails 😅). 100% local This workflow is designed to use locally-hosted open source. Ollama as LLM provider, nomic-embed-text as the embeddings model, and pgvector as the vector database engine, on top of Postgres. But.. how?! Firstly, specify the date you created your Gmail account on, then manually run the workflow in order to bulk read all your e-mail in monthly batches. Your database is now populated! Now it's the task for other workflows to query the vector database. Activate the workflow so that new e-mail is continuously added by the Gmail Trigger upon receiving it. Structured AND Vectorized This workflow stores your e-mail activity in two ways: In a structured table In a vector embeddings table And the information in both of them can be correlated by Gmail's messages id, which is stored in the vectors table as metadata property emails_metadata.id. That way consumers can benefit from both worlds! ✨ Vector similarity searches enable semantic searches, while structured queries can retrieve more factual data like the message id, its date or who it came from. Other useful templates My template Chat with Your Email History using Telegram, Mistral and Pgvector for RAG is a ready-made solution to consume this workflow. You may also pair this workflow with my other template to Email Assistant: Convert Natural Language to SQL Queries with Phi4-mini and PostgreSQL and you'll enable RAG workflows that use both structured and vectorized databases. Customizations I suppose the e-mail provider could be changed, but then you'd have to identify an alternative id field. Message-ID would be a more standard option. There are a few opinionated choices as to what metadata to store, but those shouldn't need adjustments.
by Łukasz
Who is it for? This is automation for support project manager, which helps not only to keep developres informed but also automatically keep clients in the loop - especially useful if you are managing SLA-like agreement. It is actually simple incident management board using free Kanban board, that is extended in functionality via N8N. How It Works? Script has two entry points. The first one is incident form. When incident details are provided, automation gets incident definitions from database and pushes both information to AI. AI comparse definitions with client request, refines incident priority and pushed it in NocoDB database. Second is schedule trigger, which is responsible for regular notificaitons on task status. If task is not picked up or delivered in proper time, then emails or slack messages are being sent both to client and responsible developer. How to set up? Clone automation Create (samples below) two NocoDB tables: one with definitions and second that servers as Kanban board (mind column naming!) Set up email and slack connection You should be ready to go Different incident naming If your incident level naming is different, you need to update few nodes and few columns in NocoDB. This is because incident naming must be unified through: automation flow, incident definitions and column NocoDB select fields. So be sure that following is the same: NocoDB: Incident definitions, column "Title" NocoDB: Tasks table, single select fields: "expected category" "assigned category" N8N: Incident Form "Incident Desired Category" NocoDB Tables Incident definitions table |Title |Definition |Response time|Resolution time|Default assignee| |single line text|text|number|number|email| Tasks table |email|message|expected category|internal notes|assigned category|status|expected response|expected resolution|assignee|assignee slack| |email|text|single select|text|single select|single select|date and time|date and time|email|slack username| Use kanban board Simply set up Kanban view and stack by "status" field. What's More? That's actually it. I hope that this automation will help your support line be much more streamlined! There is actually more that you could do with this automation, but it really depends on your needs. For example, you could add Email trigger to handle incoming support requests (but remember to adjust nodes accordingly). Another thing is that you could make different notification schema, depending on your needs (for example I do imagine that you may want a day or two delay before you notify client that task is after due). Thank you, perfect! Glad I could help. Visit my profile for other automations for businesses. And if you are looking for dedicated software development, do not hesitate to reach out!
by Aitor | 1Node
Talk to Your Apps: Building a Personal Assistant MCP Server with Google Gemini Wouldn't it be cool to just tell your computer or phone to "schedule a meeting with Sarah next Tuesday at 3 PM" or "find John Doe's email address" and have it actually do it? That's the dream of a personal assistant! With n8n and the power of MCP and AI models like Google Gemini, you can actually build something pretty close to that. We've put together a workflow that shows you how you can use a natural language chat interface to interact with your other apps, like your CRM, email, and calendar. What You Need to Get Started Before you dive in, you'll need a few things: n8n:** An n8n instance (either cloud or self-hosted) to build and run your workflow. Google Gemini Access:** Access to the Google Gemini model via an API key. Credentials for Your Apps:** API keys or login details for the specific CRM, Email, and Calendar services you want to connect (like Google Sheets for CRM, Gmail, Google Calendar, etc., depending on your chosen nodes). A Chat Interface:** A way to send messages to n8n to trigger the workflow (e.g., via a chat app node or webhook). How it Works (In Simple Terms) Imagine this workflow is like a helpful assistant who sits between you and your computer. Step 1: You Talk, the AI Agent Listens It all starts when you send a message through your connected chat interface. Think of this as you speaking directly to your assistant. Step 2: The Assistant's Brain (Google Gemini) Your message goes straight to the assistant's "brain." In this case, the brain is powered by a smart AI model like Google Gemini. In our template we are using the latest Gemini 2.5 Pro. But this is totally up to you. Experiment and track which model fits the kind of tasks you will pass to the agent. Its job is to understand exactly what you're asking for. Are you asking to create something? Are you asking to find information? Are you asking to update something? The brain also uses a "memory" so it can remember what you've talked about recently, making the conversation feel more natural. We are using the default context window, which is the past 5 interactions. Step 3: The Assistant Decides What Tool to Use Once the brain understands your request, the assistant figures out the best way to help you. It looks at the request and thinks, "Okay, to do this, I need to use one of my tools." Step 4: The Assistant's Toolbox (MCP & Your Apps) Here's where the "MCP" part comes in. Think of "MCP" (Model Context Protocol) as the assistant's special toolbox. Inside this toolbox are connections to all the different apps and services you use – your CRM for contacts, your email service, and your calendar. The MCP system acts like a manager for these tools, making them available to the assistant whenever they're needed. Step 5: Using the Right Tool for the Job Based on what you asked for, the assistant picks the correct tool from the toolbox. If you asked to find a contact, it grabs the "Get Contact" node from the CRM section. If you wanted to schedule a meeting, it picks the "Create Event" node from the Calendar section. If you asked to draft an email, it uses the "Draft Email" node. Step 6: The Tool Takes Action Now, the node or set of nodes get to work! It performs the action you requested within the specific app. The CRM tool finds or adds the contact. The Email tool drafts the message. The Calendar tool creates the event. Step 7: Task Completed! And just like that, your request is handled automatically, all because you simply told your assistant what you wanted in plain language. Why This is Awesome This kind of workflow shows the power of combining AI with automation platforms like n8n. You can move beyond clicking buttons and filling out forms, and instead, interact with your digital life using natural conversation. n8n makes it possible to visually build these complex connections between your chat, the AI brain, and all your different apps. Taking it Further (Possible Enhancements) This is just the start! You could enhance this personal assistant by: Connecting more apps and services (task managers, project tools, etc.). Adding capabilities to search the web or internal documents. Implementing more sophisticated memory or context handling. Getting a notification when the AI agent is done completing each task such as in Slack or Microsoft Teams. Allowing the assistant to ask clarifying questions if needed. Building a robust prompt for the AI agent. Ready to Automate Your Workflow? Imagine the dozens of hours your team could save weekly by automating repetitive tasks through a simple, natural language interface. Need help? Feel free to contact us at 1 Node. Get instant access to a library of free resources we created.